Neural Network Physically Unclonable Function: A Trainable Physically Unclonable Function System with Unassailability against Deep Learning Attacks Using Memristor Array

The dissemination of edge devices drives new requirements for security primitives for privacy protection and chip authentication. Memristors are promising entropy sources for realizing hardware‐based security primitives due to their intrinsic randomness and stochastic properties. With the adoption o...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Junkyu Park, Yoonji Lee, Hakcheon Jeong, Shinhyun Choi
Formato:	article
Lenguaje:	EN
Publicado:	Wiley 2021
Materias:	deep learning hardware security memristors physically unclonable functionss Computer engineering. Computer hardware TK7885-7895 Control engineering systems. Automatic machinery (General) TJ212-225
Acceso en línea:	https://doaj.org/article/6bc8ebf71f8b468eab3f7d56c64aa47b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:6bc8ebf71f8b468eab3f7d56c64aa47b
record_format	dspace
spelling	oai:doaj.org-article:6bc8ebf71f8b468eab3f7d56c64aa47b2021-11-23T07:58:48ZNeural Network Physically Unclonable Function: A Trainable Physically Unclonable Function System with Unassailability against Deep Learning Attacks Using Memristor Array2640-456710.1002/aisy.202100111https://doaj.org/article/6bc8ebf71f8b468eab3f7d56c64aa47b2021-11-01T00:00:00Zhttps://doi.org/10.1002/aisy.202100111https://doaj.org/toc/2640-4567The dissemination of edge devices drives new requirements for security primitives for privacy protection and chip authentication. Memristors are promising entropy sources for realizing hardware‐based security primitives due to their intrinsic randomness and stochastic properties. With the adoption of memristors among several technologies that meet essential requirements, the neural network physically unclonable function (NNPUF) is proposed, a novel PUF design that takes advantage of deep learning algorithms. The proposed design integrated with the memristor array can be constructed easily because the system does not depend on write operation accuracy. To contemplate a nondifferentiable module during training, an original concept of loss called PUF loss is devised. Iterations of weight update with the loss function bring about optimal NNPUF performance. It is shown that the design achieves a near‐ideal 50% average value for security metrics, including uniformity, diffuseness, and uniqueness. This means that the NNPUF satisfies practical quality standards for security primitives by training with PUF loss. It is also demonstrated that the NNPUF response has an unassailable resistance against deep learning‐based modeling attacks, which is verified by the near‐50% prediction model accuracy.Junkyu ParkYoonji LeeHakcheon JeongShinhyun ChoiWileyarticledeep learninghardware securitymemristorsphysically unclonable functionssComputer engineering. Computer hardwareTK7885-7895Control engineering systems. Automatic machinery (General)TJ212-225ENAdvanced Intelligent Systems, Vol 3, Iss 11, Pp n/a-n/a (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	deep learning hardware security memristors physically unclonable functionss Computer engineering. Computer hardware TK7885-7895 Control engineering systems. Automatic machinery (General) TJ212-225
spellingShingle	deep learning hardware security memristors physically unclonable functionss Computer engineering. Computer hardware TK7885-7895 Control engineering systems. Automatic machinery (General) TJ212-225 Junkyu Park Yoonji Lee Hakcheon Jeong Shinhyun Choi Neural Network Physically Unclonable Function: A Trainable Physically Unclonable Function System with Unassailability against Deep Learning Attacks Using Memristor Array
description	The dissemination of edge devices drives new requirements for security primitives for privacy protection and chip authentication. Memristors are promising entropy sources for realizing hardware‐based security primitives due to their intrinsic randomness and stochastic properties. With the adoption of memristors among several technologies that meet essential requirements, the neural network physically unclonable function (NNPUF) is proposed, a novel PUF design that takes advantage of deep learning algorithms. The proposed design integrated with the memristor array can be constructed easily because the system does not depend on write operation accuracy. To contemplate a nondifferentiable module during training, an original concept of loss called PUF loss is devised. Iterations of weight update with the loss function bring about optimal NNPUF performance. It is shown that the design achieves a near‐ideal 50% average value for security metrics, including uniformity, diffuseness, and uniqueness. This means that the NNPUF satisfies practical quality standards for security primitives by training with PUF loss. It is also demonstrated that the NNPUF response has an unassailable resistance against deep learning‐based modeling attacks, which is verified by the near‐50% prediction model accuracy.
format	article
author	Junkyu Park Yoonji Lee Hakcheon Jeong Shinhyun Choi
author_facet	Junkyu Park Yoonji Lee Hakcheon Jeong Shinhyun Choi
author_sort	Junkyu Park
title	Neural Network Physically Unclonable Function: A Trainable Physically Unclonable Function System with Unassailability against Deep Learning Attacks Using Memristor Array
title_short	Neural Network Physically Unclonable Function: A Trainable Physically Unclonable Function System with Unassailability against Deep Learning Attacks Using Memristor Array
title_full	Neural Network Physically Unclonable Function: A Trainable Physically Unclonable Function System with Unassailability against Deep Learning Attacks Using Memristor Array
title_fullStr	Neural Network Physically Unclonable Function: A Trainable Physically Unclonable Function System with Unassailability against Deep Learning Attacks Using Memristor Array
title_full_unstemmed	Neural Network Physically Unclonable Function: A Trainable Physically Unclonable Function System with Unassailability against Deep Learning Attacks Using Memristor Array
title_sort	neural network physically unclonable function: a trainable physically unclonable function system with unassailability against deep learning attacks using memristor array
publisher	Wiley
publishDate	2021
url	https://doaj.org/article/6bc8ebf71f8b468eab3f7d56c64aa47b
work_keys_str_mv	AT junkyupark neuralnetworkphysicallyunclonablefunctionatrainablephysicallyunclonablefunctionsystemwithunassailabilityagainstdeeplearningattacksusingmemristorarray AT yoonjilee neuralnetworkphysicallyunclonablefunctionatrainablephysicallyunclonablefunctionsystemwithunassailabilityagainstdeeplearningattacksusingmemristorarray AT hakcheonjeong neuralnetworkphysicallyunclonablefunctionatrainablephysicallyunclonablefunctionsystemwithunassailabilityagainstdeeplearningattacksusingmemristorarray AT shinhyunchoi neuralnetworkphysicallyunclonablefunctionatrainablephysicallyunclonablefunctionsystemwithunassailabilityagainstdeeplearningattacksusingmemristorarray
_version_	1718416831694241792

Neural Network Physically Unclonable Function: A Trainable Physically Unclonable Function System with Unassailability against Deep Learning Attacks Using Memristor Array

Ejemplares similares